# Research Papers — 2025-10 · bundle page 94 of 217

> Full-text markdown of papers #4651–4700 of 10843 published in 2025-10, newest first. AI-readable mirrors of the full 10843-paper 2025-10 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2025-10/page/94
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/93.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/95.md)

### Error analysis of a compositional score-based algorithm for simulation-based inference

Authors: Camille Touron, Gabriel V. Cardoso, Julyan Arbel, Pedro L. C. Rodrigues
Published: 2025-10-17
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.15817v2

Simulation-based inference (SBI) has become a widely used framework in applied sciences for estimating the parameters of stochastic models that best explain experimental observations. A central question in this setting is how to effectively combine multiple observations in order to improve parameter inference and obtain sharper posterior distributions. Recent advances in score-based diffusion methods address this problem by constructing a compositional score, obtained by aggregating individual posterior scores within the diffusion process. While it is natural to suspect that the accumulation of individual errors may significantly degrade sampling quality as the number of observations grows, this important theoretical issue has so far remained unexplored. In this paper, we study the compositional score produced by the GAUSS algorithm of Linhart et al. (2024) and establish an upper bound on its mean squared error in terms of both the individual score errors and the number of observations. We illustrate our theoretical findings on a Gaussian example, where all analytical expressions can be derived in a closed form.

---

### On Universality of Deep Equivariant Networks

Authors: Marco Pacini, Mircea Petrache, Bruno Lepri, Shubhendu Trivedi, Robin Walters
Published: 2025-10-17
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.15814v2

Universality results for equivariant neural networks remain rare. Those that do exist typically hold only in restrictive settings: either they rely on regular or higher-order tensor representations, leading to impractically high-dimensional hidden spaces, or they target specialized architectures, often confined to the invariant setting. This work develops a more general account. For invariant networks, we establish a universality theorem under separation constraints, showing that the addition of a fully connected readout layer secures approximation within the class of separation-constrained continuous functions. For equivariant networks, where results are even scarcer, we demonstrate that standard separability notions are inadequate and introduce the sharper criterion of $\textit{entry-wise separability}$. We show that with sufficient depth or with the addition of appropriate readout layers, equivariant networks attain universality within the entry-wise separable regime. Together with prior results showing the failure of universality for shallow models, our findings identify depth and readout layers as a decisive mechanism for universality, additionally offering a unified perspective that subsumes and extends earlier specialized results.

---

### AB-UPT for Automotive and Aerospace Applications

Authors: Benedikt Alkin, Richard Kurle, Louis Serrano, Dennis Just, Johannes Brandstetter
Published: 2025-10-17
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.15808v1

The recently proposed Anchored-Branched Universal Physics Transformers (AB-UPT) shows strong capabilities to replicate automotive computational fluid dynamics simulations requiring orders of magnitudes less compute than traditional numerical solvers. In this technical report, we add two new datasets to the body of empirically evaluated use-cases of AB-UPT, combining high-quality data generation with state-of-the-art neural surrogates. Both datasets were generated with the Luminary Cloud platform containing automotives (SHIFT-SUV) and aircrafts (SHIFT-Wing). We start by detailing the data generation. Next, we show favorable performances of AB-UPT against previous state-of-the-art transformer-based baselines on both datasets, followed by extensive qualitative and quantitative evaluations of our best AB-UPT model. AB-UPT shows strong performances across the board. Notably, it obtains near perfect prediction of integrated aerodynamic forces within seconds from a simple isotopically tesselate geometry representation and is trainable within a day on a single GPU, paving the way for industry-scale applications.

---

### Emergence of Linear Truth Encodings in Language Models

Authors: Shauli Ravfogel, Gilad Yehudai, Tal Linzen, Joan Bruna, Alberto Bietti
Published: 2025-10-17
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.15804v1

Recent probing studies reveal that large language models exhibit linear subspaces that separate true from false statements, yet the mechanism behind their emergence is unclear. We introduce a transparent, one-layer transformer toy model that reproduces such truth subspaces end-to-end and exposes one concrete route by which they can arise. We study one simple setting in which truth encoding can emerge: a data distribution where factual statements co-occur with other factual statements (and vice-versa), encouraging the model to learn this distinction in order to lower the LM loss on future tokens. We corroborate this pattern with experiments in pretrained language models. Finally, in the toy setting we observe a two-phase learning dynamic: networks first memorize individual factual associations in a few steps, then -- over a longer horizon -- learn to linearly separate true from false, which in turn lowers language-modeling loss. Together, these results provide both a mechanistic demonstration and an empirical motivation for how and why linear truth representations can emerge in language models.

---

### ERNet: Efficient Non-Rigid Registration Network for Point Sequences

Authors: Guangzhao He, Yuxi Xiao, Zhen Xu, Xiaowei Zhou, Sida Peng
Published: 2025-10-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15800v1

Registering an object shape to a sequence of point clouds undergoing non-rigid deformation is a long-standing challenge. The key difficulties stem from two factors: (i) the presence of local minima due to the non-convexity of registration objectives, especially under noisy or partial inputs, which hinders accurate and robust deformation estimation, and (ii) error accumulation over long sequences, leading to tracking failures. To address these challenges, we introduce to adopt a scalable data-driven approach and propose ERNet, an efficient feed-forward model trained on large deformation datasets. It is designed to handle noisy and partial inputs while effectively leveraging temporal information for accurate and consistent sequential registration. The key to our design is predicting a sequence of deformation graphs through a two-stage pipeline, which first estimates frame-wise coarse graph nodes for robust initialization, before refining their trajectories over time in a sliding-window fashion. Extensive experiments show that our proposed approach (i) outperforms previous state-of-the-art on both the DeformingThings4D and D-FAUST datasets, and (ii) achieves more than 4x speedup compared to the previous best, offering significant efficiency improvement.

---

### Cavity Duplexer Tuning with 1d Resnet-like Neural Networks

Authors: Anton Raskovalov
Published: 2025-10-17
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2510.15796v1

This paper presents machine learning method for tuning of cavity duplexer with a large amount of adjustment screws. After testing we declined conventional reinforcement learning approach and reformulated our task in the supervised learning setup. The suggested neural network architecture includes 1d ResNet-like backbone and processing of some additional information about S-parameters, like the shape of curve and peaks positions and amplitudes. This neural network with external control algorithm is capable to reach almost the tuned state of the duplexer within 4-5 rotations per screw.

---

### DexCanvas: Bridging Human Demonstrations and Robot Learning for Dexterous Manipulation

Authors: Xinyue Xu, Jieqiang Sun, Jing, Dai, Siyuan Chen, Lanjie Ma, Ke Sun, Bin Zhao, Jianbo Yuan, Sheng Yi, Haohua Zhu, Yiwen Lu
Published: 2025-10-17
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2510.15786v2

We present DexCanvas, a large-scale hybrid real-synthetic human manipulation dataset containing 7,000 hours of dexterous hand-object interactions seeded from 70 hours of real human demonstrations, organized across 21 fundamental manipulation types based on the Cutkosky taxonomy. Each entry combines synchronized multi-view RGB-D, high-precision mocap with MANO hand parameters, and per-frame contact points with physically consistent force profiles. Our real-to-sim pipeline uses reinforcement learning to train policies that control an actuated MANO hand in physics simulation, reproducing human demonstrations while discovering the underlying contact forces that generate the observed object motion. DexCanvas is the first manipulation dataset to combine large-scale real demonstrations, systematic skill coverage based on established taxonomies, and physics-validated contact annotations. The dataset can facilitate research in robotic manipulation learning, contact-rich control, and skill transfer across different hand morphologies.

---

### ReCon: Region-Controllable Data Augmentation with Rectification and Alignment for Object Detection

Authors: Haowei Zhu, Tianxiang Pan, Rui Qin, Jun-Hai Yong, Bin Wang
Published: 2025-10-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15783v1

The scale and quality of datasets are crucial for training robust perception models. However, obtaining large-scale annotated data is both costly and time-consuming. Generative models have emerged as a powerful tool for data augmentation by synthesizing samples that adhere to desired distributions. However, current generative approaches often rely on complex post-processing or extensive fine-tuning on massive datasets to achieve satisfactory results, and they remain prone to content-position mismatches and semantic leakage. To overcome these limitations, we introduce ReCon, a novel augmentation framework that enhances the capacity of structure-controllable generative models for object detection. ReCon integrates region-guided rectification into the diffusion sampling process, using feedback from a pre-trained perception model to rectify misgenerated regions within diffusion sampling process. We further propose region-aligned cross-attention to enforce spatial-semantic alignment between image regions and their textual cues, thereby improving both semantic consistency and overall image fidelity. Extensive experiments demonstrate that ReCon substantially improve the quality and trainability of generated data, achieving consistent performance gains across various datasets, backbone architectures, and data scales. Our code is available at https://github.com/haoweiz23/ReCon .

---

### Demo: Guide-RAG: Evidence-Driven Corpus Curation for Retrieval-Augmented Generation in Long COVID

Authors: Philip DiGiacomo, Haoyang Wang, Jinrui Fang, Yan Leng, W Michael Brode, Ying Ding
Published: 2025-10-17
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.15782v1

As AI chatbots gain adoption in clinical medicine, developing effective frameworks for complex, emerging diseases presents significant challenges. We developed and evaluated six Retrieval-Augmented Generation (RAG) corpus configurations for Long COVID (LC) clinical question answering, ranging from expert-curated sources to large-scale literature databases. Our evaluation employed an LLM-as-a-judge framework across faithfulness, relevance, and comprehensiveness metrics using LongCOVID-CQ, a novel dataset of expert-generated clinical questions. Our RAG corpus configuration combining clinical guidelines with high-quality systematic reviews consistently outperformed both narrow single-guideline approaches and large-scale literature databases. Our findings suggest that for emerging diseases, retrieval grounded in curated secondary reviews provides an optimal balance between narrow consensus documents and unfiltered primary literature, supporting clinical decision-making while avoiding information overload and oversimplified guidance. We propose Guide-RAG, a chatbot system and accompanying evaluation framework that integrates both curated expert knowledge and comprehensive literature databases to effectively answer LC clinical questions.

---

### Enhanced Renewable Energy Forecasting using Context-Aware Conformal Prediction

Authors: Alireza Moradi, Mathieu Tanneau, Reza Zandehshahvar, Pascal Van Hentenryck
Published: 2025-10-17
Categories: stat.AP, cs.LG
arXiv: https://arxiv.org/abs/2510.15780v2

Artificial intelligence (AI) is increasingly used to support renewable energy forecasting and grid operations. As renewable penetration grows, reliable probabilistic forecasting is becoming essential for managing uncertainty and supporting risk-aware operational decision-making. However, these forecasts often suffer from miscalibration due to temporal variability, changing weather conditions, and heterogeneous operating regimes. In many real-world settings, renewable energy forecasts are provided by external sources, vendors, or independently trained systems, making retraining infeasible because of limited model access or computational constraints. This creates a need for efficient and model-agnostic methods that can improve forecast reliability after they are produced. This paper presents Context-Aware Conformal Prediction (CACP), a framework for calibrating renewable energy forecasts. The proposed method relies on a weighting mechanism during the calibration procedure which assigns higher weights to historical observations that are more similar to the target forecasting condition. This enables adaptive prediction intervals that reflect local uncertainty regimes without requiring access to, or retraining of, the underlying forecasting model. Experiments are performed on a large-scale dataset from National Renewable Energy Laboratory (NREL) day-ahead solar forecasting, covering multiple systems including MISO, ERCTO, and SPP. The results show that CACP improves the reliability-efficiency tradeoff at both site and system levels compared to NREL's base forecasting model and the other conformal prediction baselines. These results suggest that CACP can serve as a practical reliability-enhancement layer for trustworthy AI-enabled renewable energy forecasting and operational decision support.

---

### Controlling the image generation process with parametric activation functions

Authors: Ilia Pavlov
Published: 2025-10-17
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.15778v1

As image generative models continue to increase not only in their fidelity but also in their ubiquity the development of tools that leverage direct interaction with their internal mechanisms in an interpretable way has received little attention In this work we introduce a system that allows users to develop a better understanding of the model through interaction and experimentation By giving users the ability to replace activation functions of a generative network with parametric ones and a way to set the parameters of these functions we introduce an alternative approach to control the networks output We demonstrate the use of our method on StyleGAN2 and BigGAN networks trained on FFHQ and ImageNet respectively.

---

### SANR: Scene-Aware Neural Representation for Light Field Image Compression with Rate-Distortion Optimization

Authors: Gai Zhang, Xinfeng Zhang, Lv Tang, Hongyu An, Li Zhang, Qingming Huang
Published: 2025-10-17
Categories: eess.IV, cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2510.15775v1

Light field images capture multi-view scene information and play a crucial role in 3D scene reconstruction. However, their high-dimensional nature results in enormous data volumes, posing a significant challenge for efficient compression in practical storage and transmission scenarios. Although neural representation-based methods have shown promise in light field image compression, most approaches rely on direct coordinate-to-pixel mapping through implicit neural representation (INR), often neglecting the explicit modeling of scene structure. Moreover, they typically lack end-to-end rate-distortion optimization, limiting their compression efficiency. To address these limitations, we propose SANR, a Scene-Aware Neural Representation framework for light field image compression with end-to-end rate-distortion optimization. For scene awareness, SANR introduces a hierarchical scene modeling block that leverages multi-scale latent codes to capture intrinsic scene structures, thereby reducing the information gap between INR input coordinates and the target light field image. From a compression perspective, SANR is the first to incorporate entropy-constrained quantization-aware training (QAT) into neural representation-based light field image compression, enabling end-to-end rate-distortion optimization. Extensive experiment results demonstrate that SANR significantly outperforms state-of-the-art techniques regarding rate-distortion performance with a 65.62\% BD-rate saving against HEVC.

---

### Self-evolving expertise in complex non-verifiable subject domains: dialogue as implicit meta-RL

Authors: Richard M. Bailey
Published: 2025-10-17
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.15772v1

So-called `wicked problems', those involving complex multi-dimensional settings, non-verifiable outcomes, heterogeneous impacts and a lack of single objectively correct answers, have plagued humans throughout history. Modern examples include decisions over justice frameworks, solving environmental pollution, planning for pandemic resilience and food security. The use of state-of-the-art artificial intelligence systems (notably Large Language Model-based agents) collaborating with humans on solving such problems is being actively explored. While the abilities of LLMs can be improved by, for example, fine-tuning, hand-crafted system prompts and scaffolding with external tools, LLMs lack endogenous mechanisms to develop expertise through experience in such settings. This work address this gap with Dialectica, a framework where agents engage in structured dialogue on defined topics, augmented by memory, self-reflection, and policy-constrained context editing. Formally, discussion is viewed as an implicit meta-reinforcement learning process. The `dialogue-trained' agents are evaluated post-hoc using judged pairwise comparisons of elicited responses. Across two model architectures (locally run Qwen3:30b and OpenAI's o4-mini) results show that enabling reflection-based context editing during discussion produces agents which dominate their baseline counterparts on Elo scores, normalized Bradley-Terry-Davidson ability, and AlphaRank mass. The predicted signatures of learning are observed qualitatively in statement and reflection logs, where reflections identify weaknesses and reliably shape subsequent statements. Agreement between quantitative and qualitative evidence supports dialogue-driven context evolution as a practical path to targeted expertise amplification in open non-verifiable domains.

---

### Concept Labels Are Not Enough: Rethinking Concept Bottleneck Models through Representation Integrity

Authors: Gaoxiang Huang, Songning Lai, Yutao Yue
Published: 2025-10-17
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.15770v4

Although deep neural networks achieve strong predictive performance, their internal reasoning often remains difficult to inspect and control. Concept Bottleneck Models (CBMs) address this opacity by factoring predictions through human-understandable concepts, thereby enabling concept-level inspection and intervention. However, CBMs remain vulnerable to concept shift and information leakage, while existing evaluations neither reveal how the internal features supporting each concept are organized nor identify the representation-level deficiency associated with these failures. We argue that this missing property is concept integrity: concept support should form a semantically coherent and non-fragmented functional group. To characterize this property, we propose group coherence (GC) and concept coverage (CC) as integrity components and aggregate them into the concept integrity score (CIS). We further introduce Concept Integrity Regularization (CIR) to encourage coherent and separated groups of concept-supporting filters. Our latent decoupled concept bottleneck model (LDCBM) applies CIR without requiring region annotations. Across three datasets, CIS rankings differ from rankings by concept and task accuracy, supporting concept integrity as a complementary representation-level criterion. Moreover, with only 10\% of concept labels, LDCBM retains approximately 93\% of its full-label task performance. Background-masking and concept-intervention further associate stronger integrity profiles with lower sensitivity to nuisance context and more responsive concept correction.

---

### Preliminary Quantitative Study on Explainability and Trust in AI Systems

Authors: Allen Daniel Sunny
Published: 2025-10-17
Categories: cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2510.15769v1

Large-scale AI models such as GPT-4 have accelerated the deployment of artificial intelligence across critical domains including law, healthcare, and finance, raising urgent questions about trust and transparency. This study investigates the relationship between explainability and user trust in AI systems through a quantitative experimental design. Using an interactive, web-based loan approval simulation, we compare how different types of explanations, ranging from basic feature importance to interactive counterfactuals influence perceived trust. Results suggest that interactivity enhances both user engagement and confidence, and that the clarity and relevance of explanations are key determinants of trust. These findings contribute empirical evidence to the growing field of human-centered explainable AI, highlighting measurable effects of explainability design on user perception

---

### On Non-interactive Evaluation of Animal Communication Translators

Authors: Orr Paradise, David F. Gruber, Adam Tauman Kalai
Published: 2025-10-17
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.15768v1

If you had an AI Whale-to-English translator, how could you validate whether or not it is working? Does one need to interact with the animals or rely on grounded observations such as temperature? We provide theoretical and proof-of-concept experimental evidence suggesting that interaction and even observations may not be necessary for sufficiently complex languages. One may be able to evaluate translators solely by their English outputs, offering potential advantages in terms of safety, ethics, and cost. This is an instance of machine translation quality evaluation (MTQE) without any reference translations available. A key challenge is identifying ``hallucinations,'' false translations which may appear fluent and plausible. We propose using segment-by-segment translation together with the classic NLP shuffle test to evaluate translators. The idea is to translate animal communication, turn by turn, and evaluate how often the resulting translations make more sense in order than permuted. Proof-of-concept experiments on data-scarce human languages and constructed languages demonstrate the potential utility of this evaluation methodology. These human-language experiments serve solely to validate our reference-free metric under data scarcity. It is found to correlate highly with a standard evaluation based on reference translations, which are available in our experiments. We also perform a theoretical analysis suggesting that interaction may not be necessary nor efficient in the early stages of learning to translate.

---

### QSilk: Micrograin Stabilization and Adaptive Quantile Clipping for Detail-Friendly Latent Diffusion

Authors: Denis Rychkovskiy
Published: 2025-10-17
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.15761v1

We present QSilk, a lightweight, always-on stabilization layer for latent diffusion that improves high-frequency fidelity while suppressing rare activation spikes. QSilk combines (i) a per-sample micro clamp that gently limits extreme values without washing out texture, and (ii) Adaptive Quantile Clip (AQClip), which adapts the allowed value corridor per region. AQClip can operate in a proxy mode using local structure statistics or in an attention entropy guided mode (model confidence). Integrated into the CADE 2.5 rendering pipeline, QSilk yields cleaner, sharper results at low step counts and ultra-high resolutions with negligible overhead. It requires no training or fine-tuning and exposes minimal user controls. We report consistent qualitative improvements across SD/SDXL backbones and show synergy with CFG/Rescale, enabling slightly higher guidance without artifacts.

---

### Poultry Farm Intelligence: An Integrated Multi-Sensor AI Platform for Enhanced Welfare and Productivity

Authors: Pieris Panagi, Savvas Karatsiolis, Kyriacos Mosphilis, Nicholas Hadjisavvas, Andreas Kamilaris, Nicolas Nicolaou, Efstathios Stavrakis, Vassilis Vassiliades
Published: 2025-10-17
Categories: cs.LG, cs.CV, cs.NE
arXiv: https://arxiv.org/abs/2510.15757v1

Poultry farming faces increasing pressure to meet productivity targets while ensuring animal welfare and environmental compliance. Yet many small and medium-sized farms lack affordable, integrated tools for continuous monitoring and decision-making, relying instead on manual, reactive inspections. This paper presents Poultry Farm Intelligence (PoultryFI) - a modular, cost-effective platform that integrates six AI-powered modules: Camera Placement Optimizer, Audio-Visual Monitoring, Analytics & Alerting, Real-Time Egg Counting, Production & Profitability Forecasting, and a Recommendation Module. Camera layouts are first optimized offline using evolutionary algorithms for full poultry house coverage with minimal hardware. The Audio-Visual Monitoring module extracts welfare indicators from synchronized video, audio, and feeding data. Analytics & Alerting produces daily summaries and real-time notifications, while Real-Time Egg Counting uses an edge vision model to automate production tracking. Forecasting models predict egg yield and feed consumption up to 10 days in advance, and the Recommendation Module integrates forecasts with weather data to guide environmental and operational adjustments. This is among the first systems to combine low-cost sensing, edge analytics, and prescriptive AI to continuously monitor flocks, predict production, and optimize performance. Field trials demonstrate 100% egg-count accuracy on Raspberry Pi 5, robust anomaly detection, and reliable short-term forecasting. PoultryFI bridges the gap between isolated pilot tools and scalable, farm-wide intelligence, empowering producers to proactively safeguard welfare and profitability.

---

### Semantic segmentation with coarse annotations

Authors: Jort de Jong, Mike Holenderski
Published: 2025-10-17
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.15756v1

Semantic segmentation is the task of classifying each pixel in an image. Training a segmentation model achieves best results using annotated images, where each pixel is annotated with the corresponding class. When obtaining fine annotations is difficult or expensive, it may be possible to acquire coarse annotations, e.g. by roughly annotating pixels in an images leaving some pixels around the boundaries between classes unlabeled. Segmentation with coarse annotations is difficult, in particular when the objective is to optimize the alignment of boundaries between classes. This paper proposes a regularization method for models with an encoder-decoder architecture with superpixel based upsampling. It encourages the segmented pixels in the decoded image to be SLIC-superpixels, which are based on pixel color and position, independent of the segmentation annotation. The method is applied to FCN-16 fully convolutional network architecture and evaluated on the SUIM, Cityscapes, and PanNuke data sets. It is shown that the boundary recall improves significantly compared to state-of-the-art models when trained on coarse annotations.

---

### NDM: A Noise-driven Detection and Mitigation Framework against Implicit Sexual Intentions in Text-to-Image Generation

Authors: Yitong Sun, Yao Huang, Ruochen Zhang, Huanran Chen, Shouwei Ruan, Ranjie Duan, Xingxing Wei
Published: 2025-10-17
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.15752v1

Despite the impressive generative capabilities of text-to-image (T2I) diffusion models, they remain vulnerable to generating inappropriate content, especially when confronted with implicit sexual prompts. Unlike explicit harmful prompts, these subtle cues, often disguised as seemingly benign terms, can unexpectedly trigger sexual content due to underlying model biases, raising significant ethical concerns. However, existing detection methods are primarily designed to identify explicit sexual content and therefore struggle to detect these implicit cues. Fine-tuning approaches, while effective to some extent, risk degrading the model's generative quality, creating an undesirable trade-off. To address this, we propose NDM, the first noise-driven detection and mitigation framework, which could detect and mitigate implicit malicious intention in T2I generation while preserving the model's original generative capabilities. Specifically, we introduce two key innovations: first, we leverage the separability of early-stage predicted noise to develop a noise-based detection method that could identify malicious content with high accuracy and efficiency; second, we propose a noise-enhanced adaptive negative guidance mechanism that could optimize the initial noise by suppressing the prominent region's attention, thereby enhancing the effectiveness of adaptive negative guidance for sexual mitigation. Experimentally, we validate NDM on both natural and adversarial datasets, demonstrating its superior performance over existing SOTA methods, including SLD, UCE, and RECE, etc. Code and resources are available at https://github.com/lorraine021/NDM.

---

### SAMix: Calibrated and Accurate Continual Learning via Sphere-Adaptive Mixup and Neural Collapse

Authors: Trung-Anh Dang, Vincent Nguyen, Ngoc-Son Vu, Christel Vrain
Published: 2025-10-17
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.15751v2

While most continual learning methods focus on mitigating forgetting and improving accuracy, they often overlook the critical aspect of network calibration, despite its importance. Neural collapse, a phenomenon where last-layer features collapse to their class means, has demonstrated advantages in continual learning by reducing feature-classifier misalignment. Few works aim to improve the calibration of continual models for more reliable predictions. Our work goes a step further by proposing a novel method that not only enhances calibration but also improves performance by reducing overconfidence, mitigating forgetting, and increasing accuracy. We introduce Sphere-Adaptive Mixup (SAMix), an adaptive mixup strategy tailored for neural collapse-based methods. SAMix adapts the mixing process to the geometric properties of feature spaces under neural collapse, ensuring more robust regularization and alignment. Experiments show that SAMix significantly boosts performance, surpassing SOTA methods in continual learning while also improving model calibration. SAMix enhances both across-task accuracy and the broader reliability of predictions, making it a promising advancement for robust continual learning systems.

---

### SEGA: A Stepwise Evolution Paradigm for Content-Aware Layout Generation with Design Prior

Authors: Haoran Wang, Bo Zhao, Jinghui Wang, Hanzhang Wang, Huan Yang, Wei Ji, Hao Liu, Xinyan Xiao
Published: 2025-10-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15749v1

In this paper, we study the content-aware layout generation problem, which aims to automatically generate layouts that are harmonious with a given background image. Existing methods usually deal with this task with a single-step reasoning framework. The lack of a feedback-based self-correction mechanism leads to their failure rates significantly increasing when faced with complex element layout planning. To address this challenge, we introduce SEGA, a novel Stepwise Evolution Paradigm for Content-Aware Layout Generation. Inspired by the systematic mode of human thinking, SEGA employs a hierarchical reasoning framework with a coarse-to-fine strategy: first, a coarse-level module roughly estimates the layout planning results; then, another refining module performs fine-level reasoning regarding the coarse planning results. Furthermore, we incorporate layout design principles as prior knowledge into the model to enhance its layout planning ability. Besides, we present GenPoster-100K that is a new large-scale poster dataset with rich meta-information annotation. The experiments demonstrate the effectiveness of our approach by achieving the state-of-the-art results on multiple benchmark datasets. Our project page is at: https://brucew91.github.io/SEGA.github.io/

---

### Towards Relaxed Multimodal Inputs for Gait-based Parkinson's Disease Assessment

Authors: Minlin Zeng, Zhipeng Zhou, Yang Qiu, Martin J. McKeown, Zhiqi Shen
Published: 2025-10-17
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.15748v2

Parkinson's disease assessment has garnered growing interest in recent years, particularly with the advent of sensor data and machine learning techniques. Among these, multimodal approaches have demonstrated strong performance by effectively integrating complementary information from various data sources. However, two major limitations hinder their practical application: (1) the need to synchronize all modalities during training, and (2) the dependence on all modalities during inference. To address these issues, we propose the first Parkinson's assessment system that formulates multimodal learning as a multi-objective optimization (MOO) problem. This not only allows for more flexible modality requirements during both training and inference, but also handles modality collapse issue during multimodal information fusion. In addition, to mitigate the imbalance within individual modalities, we introduce a margin-based class rebalancing strategy to enhance category learning. We conduct extensive experiments on three public datasets under both synchronous and asynchronous settings. The results show that our framework-Towards Relaxed InPuts (TRIP)-achieves state-of-the-art performance, outperforming the best baselines by 16.48, 6.89, and 11.55 percentage points in the asynchronous setting, and by 4.86 and 2.30 percentage points in the synchronous setting, highlighting its effectiveness and adaptability.

---

### LLMs Judge Themselves: A Game-Theoretic Framework for Human-Aligned Evaluation

Authors: Gao Yang, Yuhang Liu, Siyu Miao, Xinyue Liang, Zhengyang Liu, Heyan Huang
Published: 2025-10-17
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.15746v2

Ideal or real - that is the question.In this work, we explore whether principles from game theory can be effectively applied to the evaluation of large language models (LLMs). This inquiry is motivated by the growing inadequacy of conventional evaluation practices, which often rely on fixed-format tasks with reference answers and struggle to capture the nuanced, subjective, and open-ended nature of modern LLM behavior. To address these challenges, we propose a novel alternative: automatic mutual evaluation, where LLMs assess each other's output through self-play and peer review. These peer assessments are then systematically compared with human voting behavior to evaluate their alignment with human judgment. Our framework incorporates game-theoretic voting algorithms to aggregate peer reviews, enabling a principled investigation into whether model-generated rankings reflect human preferences. Empirical results reveal both convergences and divergences between theoretical predictions and human evaluations, offering valuable insights into the promises and limitations of mutual evaluation. To the best of our knowledge, this is the first work to jointly integrate mutual evaluation, game-theoretic aggregation, and human-grounded validation for evaluating the capabilities of LLMs.

---

### Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset

Authors: Qingyan Bai, Qiuyu Wang, Hao Ouyang, Yue Yu, Hanlin Wang, Wen Wang, Ka Leong Cheng, Shuailei Ma, Yanhong Zeng, Zichen Liu, Yinghao Xu, Yujun Shen et al.
Published: 2025-10-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15742v2

Instruction-based video editing promises to democratize content creation, yet its progress is severely hampered by the scarcity of large-scale, high-quality training data. We introduce Ditto, a holistic framework designed to tackle this fundamental challenge. At its heart, Ditto features a novel data generation pipeline that fuses the creative diversity of a leading image editor with an in-context video generator, overcoming the limited scope of existing models. To make this process viable, our framework resolves the prohibitive cost-quality trade-off by employing an efficient, distilled model architecture augmented by a temporal enhancer, which simultaneously reduces computational overhead and improves temporal coherence. Finally, to achieve full scalability, this entire pipeline is driven by an intelligent agent that crafts diverse instructions and rigorously filters the output, ensuring quality control at scale. Using this framework, we invested over 12,000 GPU-days to build Ditto-1M, a new dataset of one million high-fidelity video editing examples. We trained our model, Editto, on Ditto-1M with a curriculum learning strategy. The results demonstrate superior instruction-following ability and establish a new state-of-the-art in instruction-based video editing.

---

### AURA: An Agent Autonomy Risk Assessment Framework

Authors: Lorenzo Satta Chiris, Ayush Mishra
Published: 2025-10-17
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2510.15739v1

As autonomous agentic AI systems see increasing adoption across organisations, persistent challenges in alignment, governance, and risk management threaten to impede deployment at scale. We present AURA (Agent aUtonomy Risk Assessment), a unified framework designed to detect, quantify, and mitigate risks arising from agentic AI. Building on recent research and practical deployments, AURA introduces a gamma-based risk scoring methodology that balances risk assessment accuracy with computational efficiency and practical considerations. AURA provides an interactive process to score, evaluate and mitigate the risks of running one or multiple AI Agents, synchronously or asynchronously (autonomously). The framework is engineered for Human-in-the-Loop (HITL) oversight and presents Agent-to-Human (A2H) communication mechanisms, allowing for seamless integration with agentic systems for autonomous self-assessment, rendering it interoperable with established protocols (MCP and A2A) and tools. AURA supports a responsible and transparent adoption of agentic AI and provides robust risk detection and mitigation while balancing computational resources, positioning it as a critical enabler for large-scale, governable agentic AI in enterprise environments.

---

### Fix False Transparency by Noise Guided Splatting

Authors: Aly El Hakie, Yiren Lu, Yu Yin, Michael Jenkins, Yehe Liu
Published: 2025-10-17
Categories: cs.GR, cs.CV
arXiv: https://arxiv.org/abs/2510.15736v1

Opaque objects reconstructed by 3DGS often exhibit a falsely transparent surface, leading to inconsistent background and internal patterns under camera motion in interactive viewing. This issue stems from the ill-posed optimization in 3DGS. During training, background and foreground Gaussians are blended via alpha-compositing and optimized solely against the input RGB images using a photometric loss. As this process lacks an explicit constraint on surface opacity, the optimization may incorrectly assign transparency to opaque regions, resulting in view-inconsistent and falsely transparent. This issue is difficult to detect in standard evaluation settings but becomes particularly evident in object-centric reconstructions under interactive viewing. Although other causes of view-inconsistency have been explored recently, false transparency has not been explicitly identified. To the best of our knowledge, we are the first to identify, characterize, and develop solutions for this artifact, an underreported artifact in 3DGS. Our strategy, NGS, encourages surface Gaussians to adopt higher opacity by injecting opaque noise Gaussians in the object volume during training, requiring only minimal modifications to the existing splatting process. To quantitatively evaluate false transparency in static renderings, we propose a transmittance-based metric that measures the severity of this artifact. In addition, we introduce a customized, high-quality object-centric scan dataset exhibiting pronounced transparency issues, and we augment popular existing datasets with complementary infill noise specifically designed to assess the robustness of 3D reconstruction methods to false transparency. Experiments across multiple datasets show that NGS substantially reduces false transparency while maintaining competitive performance on standard rendering metrics, demonstrating its overall effectiveness.

---

### Attention Sinks in Diffusion Language Models

Authors: Maximo Eduardo Rulli, Simone Petruzzi, Edoardo Michielon, Fabrizio Silvestri, Simone Scardapane, Alessio Devoto
Published: 2025-10-17
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.15731v2

Masked Diffusion Language Models (DLMs) have recently emerged as a promising alternative to traditional Autoregressive Models (ARMs). DLMs employ transformer encoders with bidirectional attention, enabling parallel token generation while maintaining competitive performance. Although their efficiency and effectiveness have been extensively studied, the internal mechanisms that govern DLMs remain largely unexplored. In this work, we conduct an empirical analysis of DLM attention patterns, focusing on the attention sinking phenomenon, an effect previously observed in various transformer-based architectures. Our findings reveal that DLMs also exhibit attention sinks, but with distinct characteristics. First, unlike in ARMs, the sink positions in DLMs tend to shift throughout the generation process, displaying a dynamic behaviour. Second, while ARMs are highly sensitive to the removal of attention sinks, DLMs remain robust: masking sinks leads to only a minor degradation in performance. These results provide new insights into the inner workings of diffusion-based language models and highlight fundamental differences in how they allocate and utilize attention compared to autoregressive models.

---

### RLAF: Reinforcement Learning from Automaton Feedback

Authors: Mahyar Alinejad, Alvaro Velasquez, Yue Wang, George Atia
Published: 2025-10-17
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.15728v1

Reinforcement Learning (RL) in environments with complex, history-dependent reward structures poses significant challenges for traditional methods. In this work, we introduce a novel approach that leverages automaton-based feedback to guide the learning process, replacing explicit reward functions with preferences derived from a deterministic finite automaton (DFA). Unlike conventional approaches that use automata for direct reward specification, our method employs the structure of the DFA to generate preferences over trajectories that are used to learn a reward function, eliminating the need for manual reward engineering. Our framework introduces a static approach that uses the learned reward function directly for policy optimization and a dynamic approach that involves continuous refining of the reward function and policy through iterative updates until convergence. Our experiments in both discrete and continuous environments demonstrate that our approach enables the RL agent to learn effective policies for tasks with temporal dependencies, outperforming traditional reward engineering and automaton-based baselines such as reward machines and LTL-guided methods. Our results highlight the advantages of automaton-based preferences in handling non-Markovian rewards, offering a scalable, efficient, and human-independent alternative to traditional reward modeling. We also provide a convergence guarantee showing that under standard assumptions our automaton-guided preference-based framework learns a policy that is near-optimal with respect to the true non-Markovian objective.

---

### Invoice Information Extraction: Methods and Performance Evaluation

Authors: Sai Yashwant, Anurag Dubey, Praneeth Paikray, Gantala Thulsiram
Published: 2025-10-17
Categories: cs.AI, cs.DB
arXiv: https://arxiv.org/abs/2510.15727v2

This paper presents methods for extracting structured information from invoice documents and proposes a set of evaluation metrics (EM) to assess the accuracy of the extracted data against annotated ground truth. The approach involves pre-processing scanned or digital invoices, applying Docling and LlamaCloud Services to identify and extract key fields such as invoice number, date, total amount, and vendor details. To ensure the reliability of the extraction process, we establish a robust evaluation framework comprising field-level precision, consistency check failures, and exact match accuracy. The proposed metrics provide a standardized way to compare different extraction methods and highlight strengths and weaknesses in field-specific performance.

---

### DGME-T: Directional Grid Motion Encoding for Transformer-Based Historical Camera Movement Classification

Authors: Tingyu Lin, Armin Dadras, Florian Kleber, Robert Sablatnig
Published: 2025-10-17
Categories: cs.CV, cs.AI, eess.IV
arXiv: https://arxiv.org/abs/2510.15725v1

Camera movement classification (CMC) models trained on contemporary, high-quality footage often degrade when applied to archival film, where noise, missing frames, and low contrast obscure motion cues. We bridge this gap by assembling a unified benchmark that consolidates two modern corpora into four canonical classes and restructures the HISTORIAN collection into five balanced categories. Building on this benchmark, we introduce DGME-T, a lightweight extension to the Video Swin Transformer that injects directional grid motion encoding, derived from optical flow, via a learnable and normalised late-fusion layer. DGME-T raises the backbone's top-1 accuracy from 81.78% to 86.14% and its macro F1 from 82.08% to 87.81% on modern clips, while still improving the demanding World-War-II footage from 83.43% to 84.62% accuracy and from 81.72% to 82.63% macro F1. A cross-domain study further shows that an intermediate fine-tuning stage on modern data increases historical performance by more than five percentage points. These results demonstrate that structured motion priors and transformer representations are complementary and that even a small, carefully calibrated motion head can substantially enhance robustness in degraded film analysis. Related resources are available at https://github.com/linty5/DGME-T.

---

### ProSh: Probabilistic Shielding for Model-free Reinforcement Learning

Authors: Edwin Hamel-De le Court, Gaspard Ohlmann, Francesco Belardinelli
Published: 2025-10-17
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.15720v2

Safety is a major concern in reinforcement learning (RL): we aim at developing RL systems that not only perform optimally, but are also safe to deploy by providing formal guarantees about their safety. To this end, we introduce Probabilistic Shielding via Risk Augmentation (ProSh), a model-free algorithm for safe reinforcement learning under cost constraints. ProSh augments the Constrained MDP state space with a risk budget and enforces safety by applying a shield to the agent's policy distribution using a learned cost critic. The shield ensures that all sampled actions remain safe in expectation. We also show that optimality is preserved when the environment is deterministic. Since ProSh is model-free, safety during training depends on the knowledge we have acquired about the environment. We provide a tight upper-bound on the cost in expectation, depending only on the backup-critic accuracy, that is always satisfied during training. Under mild, practically achievable assumptions, ProSh guarantees safety even at training time, as shown in the experiments.

---

### Cost-Aware Retrieval-Augmentation Reasoning Models with Adaptive Retrieval Depth

Authors: Helia Hashemi, Victor Rühle, Saravan Rajmohan
Published: 2025-10-17
Categories: cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2510.15719v1

Reasoning models have gained significant attention due to their strong performance, particularly when enhanced with retrieval augmentation. However, these models often incur high computational costs, as both retrieval and reasoning tokens contribute substantially to the overall resource usage. In this work, we make the following contributions: (1) we propose a retrieval-augmented reasoning model that dynamically adjusts the length of the retrieved document list based on the query and retrieval results; (2) we develop a cost-aware advantage function for training of efficient retrieval-augmented reasoning models through reinforcement learning; and (3) we explore both memory- and latency-bound implementations of the proposed cost-aware framework for both proximal and group relative policy optimization algorithms. We evaluate our approach on seven public question answering datasets and demonstrate significant efficiency gains, without compromising effectiveness. In fact, we observed that the model latency decreases by ~16-20% across datasets, while its effectiveness increases by ~5% on average, in terms of exact match.

---

### Direct Preference Optimization with Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences

Authors: Keertana Chidambaram, Karthik Vinary Seetharaman, Vasilis Syrgkanis
Published: 2025-10-17
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.15716v1

Reinforcement Learning from Human Feedback (RLHF) has become central to aligning large language models with human values, typically by first learning a reward model from preference data which is then used to update the model with reinforcement learning. Recent alternatives such as Direct Preference Optimization (DPO) simplify this pipeline by directly optimizing on preferences. However, both approaches often assume uniform annotator preferences and rely on binary comparisons, overlooking two key limitations: the diversity of human evaluators and the limitations of pairwise feedback. In this work, we address both these issues. First, we connect preference learning in RLHF with the econometrics literature and show that binary comparisons are insufficient for identifying latent user preferences from finite user data and infinite users, while (even incomplete) rankings over three or more responses ensure identifiability. Second, we introduce methods to incorporate heterogeneous preferences into alignment algorithms. We develop an Expectation-Maximization adaptation of DPO that discovers latent annotator types and trains a mixture of LLMs accordingly. Then we propose an aggregation algorithm using a min-max regret fairness criterion to produce a single generative policy with equitable performance guarantees. Together, these contributions establish a theoretical and algorithmic framework for fairness and personalization for diverse users in generative model alignment.

---

### Second-Order Optimization with Asynchronous Curvature

Authors: El Mahdi Chayti, Martin Jaggi
Published: 2025-10-17
Categories: math.OC, cs.LG
arXiv: https://arxiv.org/abs/2510.15714v4

Second-order methods make fast progress per iteration, but forming and factorizing the Hessian often dominates their wall-clock time. We study \emph{Split-Client}, a task-parallel design in which a curvature client factorizes Hessians in the background while a gradient client takes cubic-regularized steps with the most recently published matrix, so that curvature cost appears as a delay rather than as blocking time. For delayed exact Hessians, we prove a first-order stationarity bound that depends on the average age of the curvature rather than its maximum, using an overlap count and a weighted Hardy inequality that allows any bounded-error initial matrix; the analysis extends to subsampled and uniformly inexact curvature. Under a fixed-cost model, the resulting wall-clock bound matches the scaling of optimally tuned Lazy Hessian without choosing a reuse period. In experiments on two LIBSVM datasets, an implementation decreases the objective earlier in wall-clock time than Lazy and Vanilla cubic Newton, with the largest gains at intermediate accuracy.

---

### UniMedVL: Unifying Medical Multimodal Understanding and Generation through Observation-Knowledge-Analysis

Authors: Junzhi Ning, Wei Li, Cheng Tang, Jiashi Lin, Chenglong Ma, Chaoyang Zhang, Jiyao Liu, Ying Chen, Shujian Gao, Yuandong Pu, Huihui Xu, Chenhui Gou et al.
Published: 2025-10-17
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15710v3

Medical workflows routinely combine reading images with producing visual and textual outputs, making both image understanding and generation central to medical AI. Most existing systems, however, address these abilities in isolated models, losing the shared knowledge that a unified architecture could exploit. To bridge this gap, we present UniMedVL, the first unified medical model that seamlessly integrates multimodal understanding and generation capabilities within a single model without switching weights. We achieve this via a tailored progressive training pipeline where understanding and generation mutually reinforce each other. To effectively train UniMedVL, we curate UniMedVL-5M, the first large-scale medical dataset comprising over 5.6M instances across 8 medical imaging modalities, tailored for multimodal input-output tasks in unified medical understanding and generation. Experimental results demonstrate that UniMedVL achieves competitive performance on five medical understanding benchmarks. Crucially, UniMedVL natively supports diverse interleaved generation tasks, e.g., virtual staining, super-resolution, cross-modal synthesis, essential for complex medical workflows. Our code and dataset are publicly available.

---

### GraphMind: Interactive Novelty Assessment System for Accelerating Scientific Discovery

Authors: Italo Luis da Silva, Hanqi Yan, Lin Gui, Yulan He
Published: 2025-10-17
Categories: cs.IR, cs.CL
arXiv: https://arxiv.org/abs/2510.15706v1

Large Language Models (LLMs) show strong reasoning and text generation capabilities, prompting their use in scientific literature analysis, including novelty assessment. While evaluating novelty of scientific papers is crucial for peer review, it requires extensive knowledge of related work, something not all reviewers have. While recent work on LLM-assisted scientific literature analysis supports literature comparison, existing approaches offer limited transparency and lack mechanisms for result traceability via an information retrieval module. To address this gap, we introduce $\textbf{GraphMind}$, an easy-to-use interactive web tool designed to assist users in evaluating the novelty of scientific papers or drafted ideas. Specially, $\textbf{GraphMind}$ enables users to capture the main structure of a scientific paper, explore related ideas through various perspectives, and assess novelty via providing verifiable contextual insights. $\textbf{GraphMind}$ enables users to annotate key elements of a paper, explore related papers through various relationships, and assess novelty with contextual insight. This tool integrates external APIs such as arXiv and Semantic Scholar with LLMs to support annotation, extraction, retrieval and classification of papers. This combination provides users with a rich, structured view of a scientific idea's core contributions and its connections to existing work. $\textbf{GraphMind}$ is available at https://oyarsa.github.io/graphmind and a demonstration video at https://youtu.be/wKbjQpSvwJg. The source code is available at https://github.com/oyarsa/graphmind.

---

### Beyond-Diagonal RIS Under Non-Idealities: Learning-Based Architecture Discovery and Optimization

Authors: Binggui Zhou, Bruno Clerckx
Published: 2025-10-17
Categories: cs.IT, cs.AI, eess.SP
arXiv: https://arxiv.org/abs/2510.15701v2

Beyond-diagonal reconfigurable intelligent surface (BD-RIS) has recently been introduced to enable advanced control over electromagnetic waves to further increase the benefits of traditional RIS in enhancing signal quality and improving spectral and energy efficiency for next-generation wireless networks. A significant issue in designing and deploying BD-RIS is the tradeoff between its performance and circuit complexity. While existing studies have explored optimal architectures to minimize circuit complexity in ideal BD-RIS, architecture discovery for non-ideal BD-RIS remains uninvestigated. Consequently, how non-idealities and circuit complexity jointly affect the performance of BD-RIS remains unclear, making it difficult to achieve the performance-circuit complexity tradeoff in the presence of non-idealities. Essentially, architecture discovery for non-ideal BD-RIS faces challenges from both the computational complexity of global architecture search and the difficulty in achieving global optima. To tackle these challenges, we propose a learning-based two-tier architecture discovery framework (LTTADF) consisting of an architecture generator and a performance optimizer to jointly discover optimal architectures for non-ideal BD-RIS given specific circuit complexities, which can effectively explore over a large architecture space while avoiding getting trapped in poor local optima and thus achieving near-optimal solutions for the performance optimization. Numerical results provide valuable insights for deploying non-ideal BD-RIS considering the performance-circuit complexity tradeoff.

---

### ProofOptimizer: Training Language Models to Simplify Proofs without Human Demonstrations

Authors: Alex Gu, Bartosz Piotrowski, Fabian Gloeckle, Kaiyu Yang, Aram H. Markosyan
Published: 2025-10-17
Categories: cs.LG, cs.AI, cs.PL
arXiv: https://arxiv.org/abs/2510.15700v1

Neural theorem proving has advanced rapidly in the past year, reaching IMO gold-medalist capabilities and producing formal proofs that span thousands of lines. Although such proofs are mechanically verified by formal systems like Lean, their excessive length renders them difficult for humans to comprehend and limits their usefulness for mathematical insight. Proof simplification is therefore a critical bottleneck. Yet, training data for this task is scarce, and existing methods -- mainly agentic scaffolding with off-the-shelf LLMs -- struggle with the extremely long proofs generated by RL-trained provers. We introduce ProofOptimizer, the first language model trained to simplify Lean proofs without requiring additional human supervision. ProofOptimizer is trained via expert iteration and reinforcement learning, using Lean to verify simplifications and provide training signal. At inference time, it operates within an iterative proof-shortening workflow, progressively reducing proof length. Experiments show that ProofOptimizer substantially compresses proofs generated by state-of-the-art RL-trained provers on standard benchmarks, reducing proof length by 87% on miniF2F, 57% on PutnamBench, and 49% on Seed-Prover's IMO 2025 proofs. Beyond conciseness, the simplified proofs check faster in Lean and further improve downstream prover performance when reused as training data for supervised finetuning.

---

### Constrained Adversarial Perturbation

Authors: Virendra Nishad, Bhaskar Mukhoty, Hilal AlQuabeh, Sandeep K. Shukla, Sayak Ray Chowdhury
Published: 2025-10-17
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.15699v1

Deep neural networks have achieved remarkable success in a wide range of classification tasks. However, they remain highly susceptible to adversarial examples - inputs that are subtly perturbed to induce misclassification while appearing unchanged to humans. Among various attack strategies, Universal Adversarial Perturbations (UAPs) have emerged as a powerful tool for both stress testing model robustness and facilitating scalable adversarial training. Despite their effectiveness, most existing UAP methods neglect domain specific constraints that govern feature relationships. Violating such constraints, such as debt to income ratios in credit scoring or packet flow invariants in network communication, can render adversarial examples implausible or easily detectable, thereby limiting their real world applicability. In this work, we advance universal adversarial attacks to constrained feature spaces by formulating an augmented Lagrangian based min max optimization problem that enforces multiple, potentially complex constraints of varying importance. We propose Constrained Adversarial Perturbation (CAP), an efficient algorithm that solves this problem using a gradient based alternating optimization strategy. We evaluate CAP across diverse domains including finance, IT networks, and cyber physical systems, and demonstrate that it achieves higher attack success rates while significantly reducing runtime compared to existing baselines. Our approach also generalizes seamlessly to individual adversarial perturbations, where we observe similar strong performance gains. Finally, we introduce a principled procedure for learning feature constraints directly from data, enabling broad applicability across domains with structured input spaces.

---

### Exploring the Synergy of Quantitative Factors and Newsflow Representations from Large Language Models for Stock Return Prediction

Authors: Tian Guo, Emmanuel Hauptmann
Published: 2025-10-17
Categories: q-fin.CP, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.15691v3

In quantitative investing, return prediction supports various tasks, including stock selection, portfolio optimization, and risk management. Quantitative factors, such as valuation, quality, and growth, capture various characteristics of stocks. Unstructured data, like news and transcripts, has attracted growing attention, driven by recent advances in large language models (LLMs). This paper examines effective methods for leveraging multimodal factors and newsflow in return prediction and stock selection. First, we introduce a fusion learning framework to learn a unified representation from factors and newsflow representations generated by an LLM. Within this framework, we compare three methods of different architectural complexities: representation combination, representation summation, and attentive representations. Next, building on the limitation of fusion learning observed in empirical comparison, we explore the mixture model that adaptively combines predictions made by single modalities and their fusion. To mitigate the training instability of the mixture model, we introduce a decoupled training approach with theoretical insights. Finally, our experiments on real investment universes yield several insights into effective multimodal modeling of factors and news for stock return prediction and selection.

---

### KS-Net: Multi-layer network model for determining the rotor type from motor parameters in interior PMSMs

Authors: Kivanc Dogan, Ahmet Orhan
Published: 2025-10-17
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.15688v1

The demand for high efficiency and precise control in electric drive systems has led to the widespread adoption of Interior Permanent Magnet Synchronous Motors (IPMSMs). The performance of these motors is significantly influenced by rotor geometry. Traditionally, rotor shape analysis has been conducted using the finite element method (FEM), which involves high computational costs. This study aims to classify the rotor shape (2D type, V type, Nabla type) of IPMSMs using electromagnetic parameters through machine learning-based methods and to demonstrate the applicability of this approach as an alternative to classical methods. In this context, a custom deep learning model, KS-Net, developed by the user, was comparatively evaluated against Cubic SVM, Quadratic SVM, Fine KNN, Cosine KNN, and Fine Tree algorithms. The balanced dataset, consisting of 9,000 samples, was tested using 10-fold cross-validation, and performance metrics such as accuracy, precision, recall, and F1-score were employed. The results indicate that the Cubic SVM and Quadratic SVM algorithms classified all samples flawlessly, achieving 100% accuracy, while the KS-Net model achieved 99.98% accuracy with only two misclassifications, demonstrating competitiveness with classical methods. This study shows that the rotor shape of IPMSMs can be predicted with high accuracy using data-driven approaches, offering a fast and cost-effective alternative to FEM-based analyses. The findings provide a solid foundation for accelerating motor design processes, developing automated rotor identification systems, and enabling data-driven fault diagnosis in engineering applications.

---

### Leveraging LLMs for Context-Aware Implicit Textual and Multimodal Hate Speech Detection

Authors: Joshua Wolfe Brook, Ilia Markov
Published: 2025-10-17
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.15685v2

This paper investigates the use of an LLM to generate auxiliary background context for social media posts, and explores four methods to incorporate this context into the input of an SBERT-based Hate Speech Detection (HSD) classifier. These are: text concatenation, embedding concatenation, a hierarchical transformer-based fusion, and LLM-driven text enhancement. We evaluate the impact of our context generation and incorporation strategies in a textual setting on the Latent Hatred dataset of implicitly hateful tweets and a multimodal setting on the MAMI dataset of misogynous internet memes. Results are evaluated against a zero-context baseline, two previous approaches based on entity linking, and a zero-shot LLM classifier. Findings indicate that incorporating generated context improves HSD performance by up to 3 and 6 F1 points on textual and multimodal settings respectively, from a zero-context baseline to the highest-performing system, based on embedding concatenation.

---

### Towards Label-Free Brain Tumor Segmentation: Unsupervised Learning with Multimodal MRI

Authors: Gerard Comas-Quiles, Carles Garcia-Cabrera, Julia Dietlmeier, Noel E. O'Connor, Ferran Marques
Published: 2025-10-17
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.15684v1

Unsupervised anomaly detection (UAD) presents a complementary alternative to supervised learning for brain tumor segmentation in magnetic resonance imaging (MRI), particularly when annotated datasets are limited, costly, or inconsistent. In this work, we propose a novel Multimodal Vision Transformer Autoencoder (MViT-AE) trained exclusively on healthy brain MRIs to detect and localize tumors via reconstruction-based error maps. This unsupervised paradigm enables segmentation without reliance on manual labels, addressing a key scalability bottleneck in neuroimaging workflows. Our method is evaluated in the BraTS-GoAT 2025 Lighthouse dataset, which includes various types of tumors such as gliomas, meningiomas, and pediatric brain tumors. To enhance performance, we introduce a multimodal early-late fusion strategy that leverages complementary information across multiple MRI sequences, and a post-processing pipeline that integrates the Segment Anything Model (SAM) to refine predicted tumor contours. Despite the known challenges of UAD, particularly in detecting small or non-enhancing lesions, our method achieves clinically meaningful tumor localization, with lesion-wise Dice Similarity Coefficient of 0.437 (Whole Tumor), 0.316 (Tumor Core), and 0.350 (Enhancing Tumor) on the test set, and an anomaly Detection Rate of 89.4% on the validation set. These findings highlight the potential of transformer-based unsupervised models to serve as scalable, label-efficient tools for neuro-oncological imaging.

---

### Mixture of Experts Approaches in Dense Retrieval Tasks

Authors: Effrosyni Sokli, Pranav Kasela, Georgios Peikos, Gabriella Pasi
Published: 2025-10-17
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2510.15683v1

Dense Retrieval Models (DRMs) are a prominent development in Information Retrieval (IR). A key challenge with these neural Transformer-based models is that they often struggle to generalize beyond the specific tasks and domains they were trained on. To address this challenge, prior research in IR incorporated the Mixture-of-Experts (MoE) framework within each Transformer layer of a DRM, which, though effective, substantially increased the number of additional parameters. In this paper, we propose a more efficient design, which introduces a single MoE block (SB-MoE) after the final Transformer layer. To assess the retrieval effectiveness of SB-MoE, we perform an empirical evaluation across three IR tasks. Our experiments involve two evaluation setups, aiming to assess both in-domain effectiveness and the model's zero-shot generalizability. In the first setup, we fine-tune SB-MoE with four different underlying DRMs on seven IR benchmarks and evaluate them on their respective test sets. In the second setup, we fine-tune SB-MoE on MSMARCO and perform zero-shot evaluation on thirteen BEIR datasets. Additionally, we perform further experiments to analyze the model's dependency on its hyperparameters (i.e., the number of employed and activated experts) and investigate how this variation affects SB-MoE's performance. The obtained results show that SB-MoE is particularly effective for DRMs with lightweight base models, such as TinyBERT and BERT-Small, consistently exceeding standard model fine-tuning across benchmarks. For DRMs with more parameters, such as BERT-Base and Contriever, our model requires a larger number of training samples to achieve improved retrieval performance. Our code is available online at: https://github.com/FaySokli/SB-MoE.

---

### SQuAI: Scientific Question-Answering with Multi-Agent Retrieval-Augmented Generation

Authors: Ines Besrour, Jingbo He, Tobias Schreieder, Michael Färber
Published: 2025-10-17
Categories: cs.IR, cs.CL
arXiv: https://arxiv.org/abs/2510.15682v1

We present SQuAI (https://squai.scads.ai/), a scalable and trustworthy multi-agent retrieval-augmented generation (RAG) framework for scientific question answering (QA) with large language models (LLMs). SQuAI addresses key limitations of existing RAG systems in the scholarly domain, where complex, open-domain questions demand accurate answers, explicit claims with citations, and retrieval across millions of scientific documents. Built on over 2.3 million full-text papers from arXiv.org, SQuAI employs four collaborative agents to decompose complex questions into sub-questions, retrieve targeted evidence via hybrid sparse-dense retrieval, and adaptively filter documents to improve contextual relevance. To ensure faithfulness and traceability, SQuAI integrates in-line citations for each generated claim and provides supporting sentences from the source documents. Our system improves faithfulness, answer relevance, and contextual relevance by up to +0.088 (12%) over a strong RAG baseline. We further release a benchmark of 1,000 scientific question-answer-evidence triplets to support reproducibility. With transparent reasoning, verifiable citations, and domain-wide scalability, SQuAI demonstrates how multi-agent RAG enables more trustworthy scientific QA with LLMs.

---

### ProofBridge: Auto-Formalization of Natural Language Proofs in Lean via Joint Embeddings

Authors: Prithwish Jana, Kaan Kale, Ahmet Ege Tanriverdi, Cruise Song, Sriram Vishwanath, Vijay Ganesh
Published: 2025-10-17
Categories: cs.LO, cs.AI
arXiv: https://arxiv.org/abs/2510.15681v3

Translating human-written mathematical theorems and proofs from natural language (NL) into formal languages (FLs) like Lean 4 has long been a significant challenge for AI. Most state-of-the-art methods either focus on theorem-only NL-to-FL auto-formalization or on FL proof synthesis from FL theorems. In practice, auto-formalization of both theorem and proof still requires human intervention, as seen in AlphaProof's silver-medal performance at the 2024 IMO, where problem statements were manually translated before automated proof synthesis. We present ProofBridge, a unified framework for automatically translating entire NL theorems and proofs into Lean 4. At its core is a joint embedding model that aligns NL and FL (NL-FL) theorem+proof pairs in a shared semantic space, enabling cross-modal retrieval of semantically relevant FL examples to guide translation. ProofBridge integrates retrieval-augmented fine-tuning with iterative proof repair, leveraging Lean's type checker and semantic equivalence feedback to ensure both syntactic correctness and semantic fidelity. Experiments show substantial improvements in proof auto-formalization over strong baselines (including GPT-5, Gemini-2.5, Kimina-Prover, DeepSeek-Prover), with our retrieval-augmented approach yielding significant gains in semantic correctness (SC, via proving bi-directional equivalence) and type correctness (TC, via type-checking theorem+proof) across pass@k metrics on miniF2F-Test-PF, a dataset we curated. In particular, ProofBridge improves cross-modal retrieval quality by up to 3.28x Recall@1 over all-MiniLM-L6-v2, and achieves +31.14% SC and +1.64% TC (pass@32) compared to the baseline Kimina-Prover-RL-1.7B.

---

### CarBoN: Calibrated Best-of-N Sampling Improves Test-time Reasoning

Authors: Yung-Chen Tang, Pin-Yu Chen, Andrea Cavallaro
Published: 2025-10-17
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.15674v1

Allocating more computation during inference time (test-time scaling) improves language model performance, especially for reasoning tasks. However, popular methods like Best-of-$N$ sampling often show diminishing returns as $N$ increases. To address this inefficiency, we introduce a general test-time calibration framework that adaptively modifies the model toward high-reward reasoning paths, with theoretical guarantees of improving the lower bound of expected reward under finite sampling, all without large language model (LLM) retraining. Within this framework, we propose CarBoN (Calibrated Best-of-$N$), a two-phase method that first explores the solution space and then learns a calibration of the logits via an input-specific temperature $T$ and additive shift vector $δ$, guiding generation toward more reliable reasoning. Experiments on MATH-500 and AIME-2024 show that CarBoN improves efficiency, with up to $4\times$ fewer rollouts to reach the same accuracy, while often achieving higher accuracy under fixed budgets. We also analyze the complementary roles of $T$ and $δ$ in balancing output diversity and correctness, and demonstrate that the framework also generalizes to step-level sampling strategies such as beam search. For more information, please refer to our project page at huggingface.co/spaces/TrustSafeAI/Test-Time-Calibration.

---

### Valeo Near-Field: a novel dataset for pedestrian intent detection

Authors: Antonyo Musabini, Rachid Benmokhtar, Jagdish Bhanushali, Victor Galizzi, Bertrand Luvison, Xavier Perrotton
Published: 2025-10-17
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.15673v1

This paper presents a novel dataset aimed at detecting pedestrians' intentions as they approach an ego-vehicle. The dataset comprises synchronized multi-modal data, including fisheye camera feeds, lidar laser scans, ultrasonic sensor readings, and motion capture-based 3D body poses, collected across diverse real-world scenarios. Key contributions include detailed annotations of 3D body joint positions synchronized with fisheye camera images, as well as accurate 3D pedestrian positions extracted from lidar data, facilitating robust benchmarking for perception algorithms. We release a portion of the dataset along with a comprehensive benchmark suite, featuring evaluation metrics for accuracy, efficiency, and scalability on embedded systems. By addressing real-world challenges such as sensor occlusions, dynamic environments, and hardware constraints, this dataset offers a unique resource for developing and evaluating state-of-the-art algorithms in pedestrian detection, 3D pose estimation and 4D trajectory and intention prediction. Additionally, we provide baseline performance metrics using custom neural network architectures and suggest future research directions to encourage the adoption and enhancement of the dataset. This work aims to serve as a foundation for researchers seeking to advance the capabilities of intelligent vehicles in near-field scenarios.

---

### A Multiclass ROC Curve

Authors: Paolo Giudici, Rosa C. Rosciano, Johanna Schrader, Delf-Magnus Kummerfeld
Published: 2025-10-17
Categories: stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2510.15670v1

This paper introduces a novel methodology for constructing multiclass ROC curves using the multidimensional Gini index. The proposed methodology leverages the established relationship between the Gini coefficient and the ROC Curve and extends it to multiclass settings through the multidimensional Gini index. The framework is validated by means of two comprehensive case studies in health care and finance. The paper provides a theoretically grounded solution to multiclass performance evaluation, particularly valuable for imbalanced datasets, for which a prudential assessment should take precedence over class frequency considerations.

---